检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Dobbins, Nicholas J. Biomedical Informatics and Data Science Department of Medicine Johns Hopkins University BaltimoreMD United States

Background: biomedical entity normalization is critical to biomedical research because the richness of free-text clinical data, such as progress notes, can often be fully leveraged only after translating words and phrases into structured and coded representations suitable for analysis. Large Language Models (LLMs), in turn, have shown great potential and high performance in a variety of natural language processing (NLP) tasks, but their application for normalization remains understudied. Methods: We applied both proprietary and open-source LLMs in combination with several rule-based normalization systems commonly used in biomedical research. We used a two-step LLM integration approach, (1) using an LLM to generate alternative phrasings of a source utterance, and (2) to prune candidate UMLS concepts, using a variety of prompting methods. We measure results by Fβ, where we favor recall over precision, and F1. Results: We evaluated a total of 5,523 concept terms and text contexts from a publicly available dataset of human-annotated biomedical abstracts. Incorporating GPT-3.5-turbo increased overall Fβ and F1 in normalization systems +9.5 and +7.3 (MetaMapLite), +13.9 and +10.9 (QuickUMLS), and +10.5 and +10.3 (BM25), while the open-source Vicuna model achieved +10.8 and +12.2 (MetaMapLite), +14.7 and +15 (QuickUMLS), and +15.6 and +18.7 (BM25). Conclusions: Existing general-purpose LLMs, both propriety and open-source, can be leveraged at scale to greatly improve normalization performance using existing tools, with no fine-tuning. © 2024, CC BY.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Desai, Pooja M. Raj, Ayush Albers, David Kashyap, Aparajita Mamykina, Lena Department of Biomedical Informatics Columbia University Irving Medical Center New YorkNY United States Columbia University Data Science Institute New YorkNY United States Department of Medicine University of Colorado AuroraCO United States Department of Biomedical Informatics Columbia University New YorkNY United States

ISBN: (纸本)9798400713958

Recommendation systems for nutrition management have become increasingly popular. Current solutions focus on optimizing for users taste preferences, often neglecting practical factors including personal priorities, existing plans, and situational constraints. We propose similarity-based meal recommendation – a novel approach that considers users existing meal plans and recommends similar meals that also align with their nutrition goals. This approach is designed to support meal decisions in on-the-spot, particularly when individuals are in constrained settings with limited options for adjustment (e.g. a cafeteria). We conducted a feasibility study with 15 participants to evaluate the utility of similarity-based recommendations in constrained settings and refine the system design. Findings show (1) a novel approach for similarity-based meal recommendations, (2) insights into the dimensions of similarity influencing actionability across diverse, and (3) opportunities to enhance user control over the system’s design. The study contributes to the advancement of human-centered AI technologies in nutrition. © 2025 Copyright held by the owner/author(s).

关键词： User centered design

来源：评论

学校读者我要写书评

暂无评论

Tomato Disease Classification Using CNN 4th

Tomato Disease Classification Using CNN

引用

4th International Conference on Smart Systems: Innovations in Computing, SSIC 2023

作者： Archanaa, N. Daniel, V. Vifert Jenuben Divya, S. Raja, Kalpana Oviya, I.R. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Sciences Amrita School of Engineering Amrita Vishwa Vidyapeetham Chennai India Section for Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States

ISBN: (纸本)9789819736898

Plant disease detection using various machine learning techniques is a very popular research area. Many promising results have been obtained, but only a few specific applications can still make farmers’ lives easier. This research focuses on the important task of identifying tomato diseases at an early stage to prevent their spread and protect crop yields more broadly, emphasizing the idea that disease prevention will more important than treatment. Leveraging the capabilities of convolutional neural networks (CNN), we developed a model that diagnoses eight distinct tomato diseases using only their images. Diseases listed include bacterial spot, early blight, late blight, leaf mold, septoria leaf spot, two-spotted spider mite, target spot, and tomato yellow leaf curl virus. An integral part of our approach involves sophisticated image prepossessing and enhancement techniques, ensuring data quality and model robustness. Feature extraction plays a key role in transforming raw image data into recognizable patterns. The architecture of the CNN has been meticulously designed, consisting of multiple layers with a notable focus on the ReLU activation function and other relevant hyper-parameters. Our main dataset comes from PlantVillage, known for synthesizing rich and diverse plant images. After rigorous training and validation, the CNN model showed exceptional accuracy of 96.88% in tomato disease identification. However, challenges such as overfitting, image quality variability, and class imbalances were encountered but were resolved through strategic data augmentation, careful CNN overlay. In summary, our research presents a practical solution for farmers and agricultural entities. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

High-Density Lipoproteins Associate with Age-Related Macular Degeneration in the All of Us Research Program

引用

Ophthalmology 2025年第6期132卷 684-691页

作者： Chen, Jimmy S. Esko, Jeffrey D. Walker, Evan Gordts, Philip L.S.M. Baxter, Sally L. Toomey, Christopher B. Division of Ophthalmology Informatics and Data Science Viterbi Family Department of Ophthalmology and Shiley Eye Institute University of California San Diego La Jolla California United States Glycobiology Research and Training Center University of California San Diego La Jolla California United States Division of Biomedical Informatics Department of Medicine University of California San Diego La Jolla California United States

Purpose: Extracellular lipoprotein aggregation is a critical event in age-related macular degeneration (AMD) pathogenesis. In this study, we sought to analyze associations between clinical and genetic-based factors related to lipoprotein metabolism and risk for AMD in the All of Us research program. Design: Cross-sectional retrospective data analysis. Participants: A total of 5028 healthy participants and 2328 patients with AMD from All of Us. Methods: Participants with and without AMD were age, race, and sex matched in a 1:2 ratio, respectively. Smoking status, history of hyperlipidemia, and statin use were extracted in a binary manner. Statin use was further subcategorized into hepatically versus nonhepatically metabolized statins. Laboratory values for low-density lipoprotein (LDL), high-density lipoprotein (HDL), and triglycerides (TGs) were also extracted, and outliers were excluded from analysis. The PLINK toolkit was used to extract single nucleotide polymorphisms (SNPs) associated with LDL and HDL dysregulation, as published in prior work. Odds ratio curves were computed to assess the risk between LDL, TG, and HDL versus AMD. All clinical and genetic variables were input into a multivariable logistic regression model, and odds ratios and P values were generated. Main Outcome Measures: Statistical significance of risk factors for AMD, thresholded at P ≤ 0.05. Results: On multivariable regression analysis, statin use and low and high HDL were significantly associated with increased AMD risk (P < 0.001 for all variables). Additionally, the multivariable regression implicated HDL-associated SNP's increased risk for AMD. Last, LPA was identified (P = 0.007) as a novel SNP associated with increased AMD risk. Conclusions: There exists a U-shaped relationship between HDL and AMD risk, such that high and low HDL are significantly associated with increased AMD risk. Additionally, SNPs associated with HDL metabolism are associated with AMD risk. This analysis further e

关键词： Drusen HDL LDL Single nucleotide polymorphism TG

来源：评论

学校读者我要写书评

暂无评论

WearMask: Fast In browser Face Mask Detection with Serverless Edge Computing for COVID 19

WearMask: Fast In browser Face Mask Detection with Serverles...

引用

IS and T International Symposium on Electronic Imaging: High Performance Computing for Imaging, HPCI 2023

作者： Wang, Zekun Wang, Pengwei Louis, Peter C. Wheless, Lee E. Huo, Yuankai Data Science Institute Vanderbilt University NashvilleTN United States Department of Information Science and Engineering Shandong University Qingdao China Department of Biomedical Informatics Vanderbilt University Medical Center NashvilleTN United States Department of Computer Science Vanderbilt University NashvilleTN United States

The COVID-19 epidemic has been a significant healthcare challenge across the world. COVID-19 is transmitted predominately by respiratory droplets generated when people breathe, talk, cough, or sneeze. Wearing a mask is the primary, effective, and convenient method of blocking 80% of respiratory infections. Therefore, many face mask detection systems have been developed to supervise hospitals, airports, publication transportation, sports venues, and retail locations. However, the current commercial solutions are typically bundled with software or hardware, impeding public accessibility. In this paper, we propose an in-browser serverless edge-computing-based face mask detection solution, called Web-based efficient AI recognition of masks (WearMask), which can be deployed on common devices (e.g., cell phones, tablets, computers) with internet connections using web browsers. The serverless edge-computing design minimizes hardware costs (e.g., specific devices or cloud computing servers). It provides a holistic edge-computing framework for integrating (1) deep learning models (YOLO), (2) high-performance neural network inference computing framework (NCNN), and (3) a stack-based virtual machine (WebAssembly). For end-users, our solution has the advantages of (1) serverless edge-computing design with minimal device limitation and privacy risk, (2) installation-free deployment, (3) low computing requirements, and (4) high detection speed. Our application has been launched with public access at ***. © 2023, Society for Imaging science and Technology.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Reply

引用

Gastroenterology 2025年第5期168卷 1040-1041页

作者： Dennis L. Shung Section of Digestive Diseases Department of Medicine Yale School of Medicine New Haven Connecticut Department of Biomedical Informatics and Data Science Yale School of Medicine New Haven Connecticut

来源：评论

学校读者我要写书评

暂无评论

Grounding Realizable Entities 15

Grounding Realizable Entities

引用

15th International Conference on Biological and biomedical Ontology, ICBO 2024

作者： Rabenberg, Michael Benson, Carter Donato, Federico He, Yongqun Huffman, Anthony Babcock, Shane Beverley, John National Center for Ontological Research United States University at Buffalo Department of Biomedical informatics United States University at Buffalo Department of Philosophy United States University of Michigan Medical School United States KadSci LLC United States Institute for Artificial Intelligence and Data Science United States

Ontological representations of qualities, dispositions, and roles have been refined over the past decade, clarifying subtle distinctions in life science research. After articulating a widely-used characterization of these entities within the context of Basic Formal Ontology (BFO), we identify gaps in this treatment and motivate the need for supplementing the BFO characterization. By way of supplement, we propose definitions for grounding relations holding between qualities and dispositions, and dispositions and roles, illustrating our proposal by representing subtle aspects of host-pathogen interactions. © 2024 Copyright for this paper by its authors.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

CDEMapper: Enhancing NIH Common data Element Normalization using Large Language Models

arXiv

引用

arXiv 2024年

作者： Wang, Yan Huang, Jimin He, Huan Zhang, Vincent Zhou, Yujia Hao, Xubing Ram, Pritham Qian, Lingfei Xie, Qianqian Weng, Ruey-Ling Lin, Fongci Hu, Yan Cui, Licong Jiang, Xiaoqian Xu, Hua Hong, Na Department of Biomedical Informatics and Data Science School of Medicine Yale University New HavenCT United States Mcwilliam School of Biomedical Informatics The University of Texas Health Science Center at Houston HoustonTX United States

Objective Common data Elements (CDEs) standardize data collection and sharing across studies, enhancing data interoperability and improving research reproducibility. However, implementing CDEs presents challenges due to the broad range and variety of data elements. This study aims to develop an effective and efficient mapping tool to bridge the gap between local data elements and National Institutes of Health (NIH) CDEs. Methods We propose CDEMapper, a large language model (LLM)-powered mapping tool designed to assist in mapping local data elements to NIH CDEs. CDEMapper has three core modules: (1) CDE indexing and embeddings. NIH CDEs were indexed and embedded to support semantic search;(2) CDE recommendations. The tool combines Elasticsearch (BM25 similarity methods) with state-of-the-art GPT services to recommend candidate CDEs and their permissible values;and (3) Human review. Users review and select the NIH CDEs/values that best match their data elements and value sets. We evaluate the tool's recommendation accuracy against manually annotated mapping results. Results CDEMapper offers a publicly available, LLM-powered, and intuitive user interface that consolidates essential and advanced mapping services into a streamlined pipeline. It provides a step-by-step, quality-assured mapping workflow designed with a user-centered approach. The evaluation results demonstrated that augmenting BM25 with GPT embeddings and a ranker consistently enhances CDEMapper's mapping accuracy in three different mapping settings across four evaluation datasets. Discussions and Conclusions This work opens up the potential of using LLMs to assist with CDE recommendation and human curation when aligning local data elements with NIH CDEs. Additionally, this effort enhances clinical research data interoperability and helps researchers better understand the gaps between local data elements and NIH CDEs. Copyright © 2024, The Authors. All rights reserved.

关键词： Clinical research

来源：评论

学校读者我要写书评

暂无评论

Initiating a One Digital Health Unified Terminology (ODH-UT) to Facilitate Community Expansion

Initiating a One Digital Health Unified Terminology (ODH-UT)...

引用

34th Medical informatics Europe Conference, MIE 2024

作者： Bauberg, Helit Nehama, Dana Blinder, Constantine Davidman, Roy Cohen, Eliyahu Tamburis, Oscar Darmoni, Stefan J. Grosjean, Julien Benis, Arriel Department of Data Science Holon Institute of Technology Israel Faculty of Industrial Engineering and Technology Management Holon Institute of Technology Israel Institute of Biostructures and Bioimaging National Research Council Naples Italy Department of Biomedical Informatics Rouen University Hospital France LIMICS Laboratory of Medical Informatics and Knowledge Engineering in e-Health INSERM U1142 Sorbonne Université France Department of Digital Medical Technologies Science Holon Institute of Technology Israel

ISBN: (纸本)9781643685335

One Digital Health (ODH) merges the Digital Health and One Health approaches to create a comprehensive framework for future health ecosystems. In this rapidly evolving field, a standardized vocabulary is not just a convenience, but a necessity to ensure efficient communication. This research proposes the development of a "One Digital Health-Unified Terminology" (ODH-UT) to facilitate communication among researchers and practitioners in Digital Health and One Health, addressing this crucial need. © 2024 The Authors.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Information Extraction from Clinical Notes: Are We Ready to Switch to Large Language Models?

arXiv

引用

arXiv 2024年

作者： Hu, Yan Zuo, Xu Zhou, Yujia Peng, Xueqing Huang, Jimin Keloth, Vipina K. Zhang, Vincent J. Weng, Ruey-Ling Chen, Qingyu Jiang, Xiaoqian Roberts, Kirk E. Xu, Hua McWilliams School of Biomedical Informatics The University of Texas Health Science Center at Houston HoustonTX United States Department of Biomedical Informatics and Data Science Yale School of Medicine Yale University New Haven United States

Backgrounds: Information extraction (IE) is critical in clinical natural language processing (NLP). While large language models (LLMs) excel on generative tasks, their performance on extractive tasks remains debated. Methods: We investigated two fundamental clinical IE tasks: Named Entity Recognition (NER) and Relation Extraction (RE). Using 1,588 clinical notes from four data sources including UT Physicians (UTP), MTSamples, MIMIC-III, and i2b2, we developed a comprehensive annotated corpus covering 4 main clinical entities (problems, tests, medications, and other treatments) and 16 modifiers (e.g., negation, certainty). We instruction-tuned LLaMA-2 and LLaMA-3 for both tasks, comparing their performance, generalizability, computational resources, and throughput to BERT. Results: LLaMA models consistently outperformed BERT across datasets and tasks. With sufficient training data (e.g., UTP), LLaMA showed marginal improvements (1% on NER, 1.5-3.7% on RE) over BERT;for limited training data (e.g., MTSamples, MIMIC-III), the improvements were greater. On the unseen i2b2 dataset, LLaMA-3-70B outperformed BERT by over 7% (F1) on NER and 4% (F1) on RE. However, LLaMA models required significantly more computing resources (i.e., memory and GPUs) and ran up to 28 times slower than BERT. To facilitate LLM use in clinical IE, we implemented"Kiwi," a clinical IE package featuring both BERT and LLaMA models and made it available at https://***/. Conclusion: This study is among the first to develop and evaluate a comprehensive clinical IE system using open-source LLMs. Results indicate that LLaMA models outperform BERT for clinical NER and RE but with higher computational costs and lower throughputs. These findings highlight that choosing between LLMs and traditional deep learning methods for clinical IE applications should remain task-specific, taking into account both performance metrics and practical considerations such as available computing resources and t

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：